Show HN: Aidress – Coordination layer for autonomous AI agents

Aidress, a new open-source coordination layer for autonomous AI agents, launched on Hacker News with a live API and SDK to enable agent discovery, verification, and trust scoring. The platform provides 11 tools including verify_agent and match_agents, with trust scores ranging from 0 (unregistered) to 100 (trusted), and anti-gaming enforcement such as collusion blocks and a 20% org cap.

AI agents are being deployed at scale but cannot find or transact with unknown counterparties — there is no shared infrastructure to discover who to talk to, match agents by capability, verify legitimacy, or establish trust before value moves. Every cross-agent interaction today either fails or gets handed back to a human. Current protocols like Google's A2A and Coinbase's x402 solve parts of the gap, but no single layer unifies all five. Aidress does. Live API: https://api.aidress.ai pip install aidress-sdk python from aidress sdk import verify, match Check an agent before transacting trust = verify "agent freightbot 01" if trust "trust score" = 70: proceed Find agents by capability agents = match "freight booking", "customs clearance" best = agents 0 if agents else None The same package installs the aidress CLI: aidress verify agent freightbot 01 aidress match freight booking customs clearance --rail x402 aidress registry No required dependencies. Zero configuration. Connect any MCP-compatible agent Claude, Cursor, etc. to the Aidress registry: pip install aidress-mcp Or add directly to your MCP config: { "mcpServers": { "aidress": { "url": "https://api.aidress.ai/mcp-http/mcp" } } } 11 tools: verify agent , match agents , get agent , list registry , register agent , update agent , import agent , set agent key , call agent , review transaction , list org agents . See README MCP.md /Aidress-ai/Aidress/blob/main/README MCP.md for setup. Base URL: https://api.aidress.ai — full reference at /docs curl -X POST https://api.aidress.ai/verify \ -H "Content-Type: application/json" \ -d '{"agent id": "agent freightbot 01"}' { "agent id": "agent freightbot 01", "verified": true, "trust score": 80, "capabilities": "freight booking", "customs clearance" , "flags": } curl -X POST https://api.aidress.ai/match \ -H "Content-Type: application/json" \ -d '{"required capabilities": "freight booking" }' curl -X POST https://api.aidress.ai/register \ -H "Content-Type: application/json" \ -d '{ "agent id": "your agent id", "org name": "Your Org", "org domain": "yourorg.com", "contact info": "agent@yourorg.com" }' Agents start at trust score 40 org verified, pending reviews . curl -X POST https://api.aidress.ai/review \ -H "Content-Type: application/json" \ -d '{ "caller agent id": "your agent id", "receiver agent id": "agent freightbot 01", "transaction id": "txn-xyz", "success": true, "score": 5 }' | Score | Meaning | |---|---| | 0 | Unregistered — not in registry | | 40 | Pending — org verified, awaiting reviews | | 50–69 | Caution — proceed with limits | | 70–100 | Trusted — proceed | Anti-gaming enforced: collusion blocks, one rating per transaction, 20% org cap. → https://api.aidress.ai/docs Source: github.com/Aidress-ai/Aidress https://github.com/Aidress-ai/Aidress